Optimizing a-DCF for Spoofing-Robust Speaker Verification
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913713839144960 |
|---|---|
| author | Kurnaz, Oğuzhan Mishra, Jagabandhu Kinnunen, Tomi H. Hanilçi, Cemal |
| author_facet | Kurnaz, Oğuzhan Mishra, Jagabandhu Kinnunen, Tomi H. Hanilçi, Cemal |
| contents | Automatic speaker verification (ASV) systems are vulnerable to spoofing attacks. We propose a spoofing-robust ASV system optimized directly for the recently introduced architecture-agnostic detection cost function (a-DCF), which allows targeting a desired trade-off between the contradicting aims of user convenience and robustness to spoofing. We combine a-DCF and binary cross-entropy (BCE) with a novel straightforward threshold optimization technique. Our results with an embedding fusion system on ASVspoof2019 data demonstrate relative improvement of $13\%$ over a system trained using BCE only (from minimum a-DCF of $0.1445$ to $0.1254$). Using an alternative non-linear score fusion approach provides relative improvement of $43\%$ (from minimum a-DCF of $0.0508$ to $0.0289$). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_04034 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Optimizing a-DCF for Spoofing-Robust Speaker Verification Kurnaz, Oğuzhan Mishra, Jagabandhu Kinnunen, Tomi H. Hanilçi, Cemal Audio and Speech Processing Automatic speaker verification (ASV) systems are vulnerable to spoofing attacks. We propose a spoofing-robust ASV system optimized directly for the recently introduced architecture-agnostic detection cost function (a-DCF), which allows targeting a desired trade-off between the contradicting aims of user convenience and robustness to spoofing. We combine a-DCF and binary cross-entropy (BCE) with a novel straightforward threshold optimization technique. Our results with an embedding fusion system on ASVspoof2019 data demonstrate relative improvement of $13\%$ over a system trained using BCE only (from minimum a-DCF of $0.1445$ to $0.1254$). Using an alternative non-linear score fusion approach provides relative improvement of $43\%$ (from minimum a-DCF of $0.0508$ to $0.0289$). |
| title | Optimizing a-DCF for Spoofing-Robust Speaker Verification |
| topic | Audio and Speech Processing |
| url | https://arxiv.org/abs/2407.04034 |